Interpretable Filter Learning Using Soft Self-attention For Raw Waveform Speech Recognition

Speech recognition from raw waveform involves learning the spectral decomposition of the signal in the first layer of the neural acoustic model using a convolution layer. In this work, we propose a raw waveform convolutional filter learning approach using soft self-attention. The acoustic filter bank in the proposed model is implemented using a parametric cosine-modulated Gaussian filter bank whose parameters are learned. A network-in-network architecture provides self-attention to generate attention weights over the sub-band filters. The attention weighted log filter bank energies are fed to the acoustic model for the task of speech recognition. Experiments are conducted on Aurora-4 (additive noise with channel artifact), and CHiME-3 (additive noise with reverberation) databases. In these experiments, the attention based filter learning approach provides considerable improvements in ASR performance over the baseline mel filter-bank features and other robust front-ends (average relative improvement of 7% in word error rate over baseline features on Aurora-4 dataset, and 5% on CHiME-3 database). Using the self-attention weights, we also present an analysis on the interpretability of the filters for the ASR task.